{"id":"https://openalex.org/W7130421768","doi":"https://doi.org/10.1109/o-cocosda68185.2025.11384917","title":"Exploring Rhythm Formant Analysis for Indic Language Classification","display_name":"Exploring Rhythm Formant Analysis for Indic Language Classification","publication_year":2025,"publication_date":"2025-11-12","ids":{"openalex":"https://openalex.org/W7130421768","doi":"https://doi.org/10.1109/o-cocosda68185.2025.11384917"},"language":null,"primary_location":{"id":"doi:10.1109/o-cocosda68185.2025.11384917","is_oa":false,"landing_page_url":"https://doi.org/10.1109/o-cocosda68185.2025.11384917","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 28th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039751618","display_name":"Parismita Gogoi","orcid":"https://orcid.org/0000-0002-2239-3584"},"institutions":[{"id":"https://openalex.org/I1317621060","display_name":"Indian Institute of Technology Guwahati","ror":"https://ror.org/0022nd079","country_code":"IN","type":"education","lineage":["https://openalex.org/I1317621060"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Parismita Gogoi","raw_affiliation_strings":["Indian Institute of Technology Guwahati,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Guwahati,India","institution_ids":["https://openalex.org/I1317621060"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034547622","display_name":"Sishir Kalita","orcid":"https://orcid.org/0009-0005-9850-3953"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sishir Kalita","raw_affiliation_strings":["Armsoftech.air,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Armsoftech.air,India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006141263","display_name":"Priyankoo Sarmah","orcid":"https://orcid.org/0000-0002-9051-1255"},"institutions":[{"id":"https://openalex.org/I1317621060","display_name":"Indian Institute of Technology Guwahati","ror":"https://ror.org/0022nd079","country_code":"IN","type":"education","lineage":["https://openalex.org/I1317621060"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Priyankoo Sarmah","raw_affiliation_strings":["Indian Institute of Technology Guwahati,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Guwahati,India","institution_ids":["https://openalex.org/I1317621060"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5126307733","display_name":"S.R Mahadeva Prasanna","orcid":null},"institutions":[{"id":"https://openalex.org/I4210152718","display_name":"Indian Institute of Technology Dharwad","ror":"https://ror.org/0509djg30","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210152718"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"S.R Mahadeva Prasanna","raw_affiliation_strings":["Indian Institute of Technology Dharwad,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Dharwad,India","institution_ids":["https://openalex.org/I4210152718"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.72486972,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10403","display_name":"Phonetics and Phonology Research","score":0.649399995803833,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10403","display_name":"Phonetics and Phonology Research","score":0.649399995803833,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.21480000019073486,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.024700000882148743,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/formant","display_name":"Formant","score":0.8626999855041504},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.8105999827384949},{"id":"https://openalex.org/keywords/rhythm","display_name":"Rhythm","score":0.7422999739646912},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5009999871253967},{"id":"https://openalex.org/keywords/frequency-domain","display_name":"Frequency domain","score":0.39820000529289246},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.39079999923706055},{"id":"https://openalex.org/keywords/basis","display_name":"Basis (linear algebra)","score":0.34310001134872437},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3310999870300293}],"concepts":[{"id":"https://openalex.org/C158215666","wikidata":"https://www.wikidata.org/wiki/Q1414685","display_name":"Formant","level":3,"score":0.8626999855041504},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8105999827384949},{"id":"https://openalex.org/C135343436","wikidata":"https://www.wikidata.org/wiki/Q170406","display_name":"Rhythm","level":2,"score":0.7422999739646912},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.597599983215332},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5009999871253967},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4715000092983246},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46650001406669617},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.39820000529289246},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.39079999923706055},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3531000018119812},{"id":"https://openalex.org/C12426560","wikidata":"https://www.wikidata.org/wiki/Q189569","display_name":"Basis (linear algebra)","level":2,"score":0.34310001134872437},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3310999870300293},{"id":"https://openalex.org/C178009071","wikidata":"https://www.wikidata.org/wiki/Q93344","display_name":"Trigonometric functions","level":2,"score":0.3249000012874603},{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.314300000667572},{"id":"https://openalex.org/C123079801","wikidata":"https://www.wikidata.org/wiki/Q750240","display_name":"Modulation (music)","level":2,"score":0.3124000132083893},{"id":"https://openalex.org/C2983668108","wikidata":"https://www.wikidata.org/wiki/Q280453","display_name":"Spectral analysis","level":3,"score":0.30469998717308044},{"id":"https://openalex.org/C110083411","wikidata":"https://www.wikidata.org/wiki/Q1744628","display_name":"Statistical classification","level":2,"score":0.303600013256073},{"id":"https://openalex.org/C2221639","wikidata":"https://www.wikidata.org/wiki/Q2877","display_name":"Discrete cosine transform","level":3,"score":0.295199990272522},{"id":"https://openalex.org/C103824480","wikidata":"https://www.wikidata.org/wiki/Q185889","display_name":"Time domain","level":2,"score":0.26840001344680786},{"id":"https://openalex.org/C201905106","wikidata":"https://www.wikidata.org/wiki/Q183755","display_name":"Amplitude modulation","level":4,"score":0.26750001311302185},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.2669999897480011},{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.25679999589920044},{"id":"https://openalex.org/C180205008","wikidata":"https://www.wikidata.org/wiki/Q159190","display_name":"Amplitude","level":2,"score":0.25279998779296875}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/o-cocosda68185.2025.11384917","is_oa":false,"landing_page_url":"https://doi.org/10.1109/o-cocosda68185.2025.11384917","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 28th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.55675208568573,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"},{"score":0.42367228865623474,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1707296401","https://openalex.org/W1805769922","https://openalex.org/W2151534428","https://openalex.org/W2167753501","https://openalex.org/W2898999375","https://openalex.org/W2963885369","https://openalex.org/W2982660737","https://openalex.org/W3003257820","https://openalex.org/W3181865509","https://openalex.org/W3194802487","https://openalex.org/W4220991896","https://openalex.org/W4239510810","https://openalex.org/W4251326366","https://openalex.org/W4280517814","https://openalex.org/W4286510434","https://openalex.org/W4372266670","https://openalex.org/W4402112143","https://openalex.org/W4402229417","https://openalex.org/W4402684123","https://openalex.org/W4406248111"],"related_works":[],"abstract_inverted_index":{"The":[0,65],"present":[1],"work":[2],"conducts":[3],"an":[4,97],"initial":[5],"exploration":[6],"of":[7,38,99,106,111,120,129],"quantitative":[8],"frequency":[9,41],"domain":[10],"rhythm":[11,27,78,125],"cues":[12,86],"for":[13,87,126],"classifying":[14],"six":[15,113],"Indian":[16],"languages:":[17],"Bengali,":[18],"Kannada,":[19],"Malayalam,":[20],"Marathi,":[21],"Telugu,":[22],"and":[23,40,62,70,101],"Tamil.":[24],"We":[25],"utilize":[26],"formants":[28],"(R-formants)":[29],"analysis":[30,37],"(RFA),":[31],"which":[32],"employs":[33],"low-frequency":[34],"(LF)":[35],"spectral":[36,63,71],"amplitude":[39],"modulation":[42],"envelopes":[43],"to":[44],"define":[45],"speech":[46,124],"rhythm.":[47],"Multiple":[48],"metrics":[49,72],"are":[50],"derived":[51,80,93],"from":[52,81],"the":[53,109,112,118,127],"LF":[54,82],"spectrum,":[55],"encompassing":[56],"R-formants,":[57],"discrete":[58],"cosine":[59],"transform-based":[60],"metrics,":[61],"metrics.":[64],"results":[66],"reveal":[67],"that":[68],"threshold-based":[69],"outperform":[73],"directly":[74],"calculated":[75],"R-formants.":[76],"Temporal":[77],"patterns":[79],"spectrograms":[83],"provide":[84],"stronger":[85],"language":[88],"discrimination.":[89],"By":[90],"integrating":[91],"all":[92],"features,":[94],"we":[95],"attain":[96],"accuracy":[98],"78.12%":[100],"a":[102],"weighted":[103],"F1":[104],"score":[105],"78.18%":[107],"in":[108,122],"classification":[110,128],"languages.":[114,131],"This":[115],"research":[116],"illustrates":[117],"effectiveness":[119],"RFA":[121],"defining":[123],"Indic":[130]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-02-19T00:00:00"}
